Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    diagram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jí
    -0.07
     Ara
    -0.06
     energy
    -0.06
     emojis
    -0.06
     subsidies
    -0.06
     Jud
    -0.06
     法
    -0.06
     Dex
    -0.06
     devote
    -0.06
    LEEP
    -0.06
    POSITIVE LOGITS
    �
    0.08
    .TextAlignment
    0.07
    VarChar
    0.06
    none
    0.06
    .EventArgs
    0.06
    δ
    0.06
    netinet
    0.06
      
    0.06
    .Socket
    0.06
     LoginComponent
    0.06
    Act Density 0.002%

    No Known Activations